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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95136
    Prev
    Next
    INDEX
    Explanations

    Questions/thoughts

    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
     "..\..\..\
    -0.78
    principalColumn
    -0.71
    bootstrapcdn
    -0.68
    rrggbb
    -0.63
    <?
    -0.60
     "..\..\
    -0.59
    '].'
    -0.57
    Datuak
    -0.57
    Hauptartikel
    -0.56
    .')
    -0.56
    POSITIVE LOGITS
     any
    0.71
    any
    0.60
     ANY
    0.49
     nào
    0.48
     Any
    0.48
     anything
    0.47
     anybody
    0.46
    NotSupported
    0.45
     anyone
    0.44
    Any
    0.44
    Activations Density 0.001%

    No Known Activations