© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 2871
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    40.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    sentence structures involving legal or formal language

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    pyvene/gemma-reft-r1-9b-it-res/l20
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     einzu
    -0.32
    -]
    -0.30
    '}}>
    -0.30
    ))^{
    -0.29
    }}>
    -0.29
    ]},
    -0.29
    -}
    -0.29
    oprecip
    -0.28
    ]}>
    -0.28
     off
    -0.28
    POSITIVE LOGITS
    
    0.72
    rrggbb
    0.65
     ég
    0.55
    URLException
    0.55
    setVerticalGroup
    0.54
    RTCF
    0.53
    ſo
    0.52
     Bí
    0.52
    Портали
    0.52
     purpoſe
    0.52
    Activations Density 1.346%

    No Known Activations