© 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. 91003
    Prev
    Next
    INDEX
    Explanations

    dissip

    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
    AAT
    -0.57
    ń
    -0.56
    JspWriter
    -0.53
    <bos>
    -0.52
    cles
    -0.48
    /***/
    -0.45
     spell
    -0.45
     clogs
    -0.45
     Cort
    -0.44
    úš
    -0.43
    POSITIVE LOGITS
    
    0.82
    theless
    0.79
    ElementException
    0.76
    ature
    0.69
    Externé
    0.69
     StringTokenizer
    0.65
    ressee
    0.64
     tartalomajánló
    0.64
    ations
    0.63
     ++)
    0.63
    Activations Density 1.679%

    No Known Activations