© 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. 1-CLT-HP
    4. 12270
    Prev
    Next
    INDEX
    Explanations

    rehabilitation

    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
    \{\\
    -0.76
    ConstraintMaker
    -0.72
    protoimpl
    -0.69
     الحره
    -0.66
    ArrowToggle
    -0.64
     Roskov
    -0.62
     Meksiku
    -0.60
    osis
    -0.59
    veien
    -0.59
    Geplaatst
    -0.58
    POSITIVE LOGITS
     ref
    0.46
     gepubliceerd
    0.43
    ukunft
    0.43
    userManager
    0.43
     referee
    0.42
    becue
    0.40
     fura
    0.40
    mappedBy
    0.40
    DockStyle
    0.40
    iffel
    0.40
    Activations Density 0.006%

    No Known Activations