© 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. 0-CLT-HP
    7. 39801
    Prev
    Next
    INDEX
    Explanations

    top

    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
    })->
    -0.50
    GOTREF
    -0.45
    __).
    -0.43
    ,:);
    -0.41
     top
    -0.41
     }$
    -0.41
    /'.$
    -0.41
     Top
    -0.40
    ({});
    -0.40
    /"+
    -0.39
    POSITIVE LOGITS
     nakalista
    0.73
    <bos>
    0.66
     AppCompatTheme
    0.63
    Rè
    0.63
     ettiği
    0.61
    UIControlState
    0.60
    __(/*!
    0.60
     withal
    0.60
    IFESTYLE
    0.60
     pleaſure
    0.60
    Activations Density 0.030%

    No Known Activations