© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96094
    Prev
    Next
    INDEX
    Explanations

    Refrigerators and freezers

    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
     AttributeSet
    -0.54
     kept
    -0.54
     getIntent
    -0.50
    kept
    -0.50
     }}"></
    -0.49
    ]^{-
    -0.49
     Kept
    -0.49
    uette
    -0.48
    scored
    -0.48
    ISHI
    -0.48
    POSITIVE LOGITS
     Einzelnen
    0.55
     estekak
    0.54
    Abitanti
    0.52
    #+#
    0.50
     învă
    0.49
    RTLR
    0.48
    RTEX
    0.48
    __*/
    0.47
     autorytatywna
    0.47
    WritableDatabase
    0.47
    Activations Density 0.000%

    No Known Activations