Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74490
    Prev
    Next
    INDEX
    Explanations

    }

    np_max-act-logits · 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
     scheme
    -0.57
    PerformLayout
    -0.57
     Scheme
    -0.49
    sonaro
    -0.41
     Unto
    -0.41
    RenderAtEndOf
    -0.40
     SCHEME
    -0.40
     Kae
    -0.40
     zostać
    -0.39
     navideñas
    -0.39
    POSITIVE LOGITS
    Autoritní
    0.63
     initComponents
    0.60
     fumée
    0.59
    ็จ
    0.57
    verwijspagina
    0.56
     กรัม
    0.56
    ApiModelProperty
    0.54
    Viited
    0.54
    elashes
    0.54
     humo
    0.53
    Activations Density 0.025%

    No Known Activations