© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96993
    Prev
    Next
    INDEX
    Explanations

    called

    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
    da
    -0.49
    bir
    -0.39
    r
    -0.39
     or
    -0.36
    ly
    -0.36
    va
    -0.36
     on
    -0.35
    ca
    -0.35
    le
    -0.35
    に
    -0.34
    POSITIVE LOGITS
     дописавши
    0.88
    WithIOException
    0.85
    ^(@)
    0.82
     ExecuteAsync
    0.76
    qrstuvwxyz
    0.74
    })`
    0.74
     ProtoMessage
    0.73
    ]));
    
    0.72
     MotionEvent
    0.72
    "):
    
    0.71
    Activations Density 0.004%

    No Known Activations