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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2853
    Prev
    Next
    INDEX
    Explanations

    Photo captions

    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
    SPATH
    -0.65
     pleaſure
    -0.59
    neurial
    -0.58
    WebVitals
    -0.58
     purpoſe
    -0.57
     myſelf
    -0.57
    soever
    -0.56
    脚注の使い方
    -0.55
     ſche
    -0.54
    TargetException
    -0.54
    POSITIVE LOGITS
    )
    1.53
    ),
    1.30
    ).
    1.25
    )
    
    1.24
    .)
    1.20
    !)
    1.18
    ):
    1.12
     )
    1.07
    ())
    1.06
    ?)
    1.05
    Activations Density 0.008%

    No Known Activations