© 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-2-2B
    5. 0-CLT-HP
    7. 94201
    Prev
    Next
    INDEX
    Explanations

    anything

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſhe
    -0.79
     Tacitus
    -0.75
     deſt
    -0.75
     paroisse
    -0.74
     Jefus
    -0.74
     ſta
    -0.73
     itſelf
    -0.72
     raiſ
    -0.70
     ―――――
    -0.69
     samfun
    -0.69
    POSITIVE LOGITS
    IsContent
    0.50
     you
    0.47
     u
    0.43
    >--}}
    0.42
    gameserver
    0.42
    getUid
    0.40
     ©️
    0.40
    ||}
    0.39
    }}}}
    0.37
     is
    0.37
    Activations Density 0.507%

    No Known Activations