© 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. 1-CLT-HP
    7. 12989
    Prev
    Next
    INDEX
    Explanations

    mining

    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
     Mine
    -0.70
     mined
    -0.69
     mine
    -0.69
    __':
    -0.68
    +:+
    -0.65
     MINE
    -0.65
    mergeFrom
    -0.64
     MINES
    -0.64
    adpleegd
    -0.64
     mines
    -0.64
    POSITIVE LOGITS
    ISupport
    0.51
    VolleyError
    0.48
    Scénario
    0.47
    魂
    0.46
    IEE
    0.46
    lem
    0.45
    engine
    0.45
     realisation
    0.45
    esModule
    0.45
    eeq
    0.45
    Activations Density 0.017%

    No Known Activations