© 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. 5-CLT-HP
    7. 1179
    Prev
    Next
    INDEX
    Explanations

    technology and computing

    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
     hObject
    -0.54
     strane
    -0.53
    featureID
    -0.52
    žas
    -0.51
    letterSpacing
    -0.50
    Descripció
    -0.50
    OGND
    -0.49
     externi
    -0.49
    cerin
    -0.49
     tork
    -0.49
    POSITIVE LOGITS
    DebuggerNonUser
    0.59
    createServer
    0.52
     TType
    0.52
    reviewer
    0.47
     reviewer
    0.47
    GOAL
    0.47
    SqlParameter
    0.46
    évaluateur
    0.45
     rul
    0.45
    FOOTNOTES
    0.45
    Activations Density 0.004%

    No Known Activations