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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74337
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text

    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
    expandindo
    -0.69
    webElement
    -0.69
    featureID
    -0.69
     []:
    -0.65
     مشين
    -0.58
    tableFuture
    -0.56
    FailureListener
    -0.54
    клопе
    -0.53
    NgModule
    -0.52
     initComponents
    -0.51
    POSITIVE LOGITS
     Situation
    0.53
    quitos
    0.52
     spare
    0.51
     Armory
    0.49
    󠁢
    0.49
     Brücke
    0.48
     Sy
    0.48
    NameValuePair
    0.48
     Sur
    0.47
     Beats
    0.46
    Activations Density 0.000%

    No Known Activations