© 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. 5-CLT-HP
    4. 94851
    Prev
    Next
    INDEX
    Explanations

    Introduces a statement/result

    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
    
    -0.65
    기도
    -0.64
    ngdoc
    -0.59
    principalColumn
    -0.58
     Otras
    -0.58
     Administrativna
    -0.56
    ABAD
    -0.56
    sslich
    -0.53
    PerformLayout
    -0.51
     Outros
    -0.51
    POSITIVE LOGITS
     we
    0.86
     he
    0.77
     ostavi
    0.61
     I
    0.60
     a
    0.58
     they
    0.56
    PreferredItem
    0.54
     here
    0.52
     shown
    0.52
     you
    0.51
    Activations Density 0.007%

    No Known Activations