© 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. 20-CLT-HP
    7. 74743
    Prev
    Next
    INDEX
    Explanations

    on

    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
    ConstraintMaker
    -0.98
     Administrativna
    -0.68
     AttributeSet
    -0.67
     TestBed
    -0.65
     يتيمه
    -0.61
     @"/
    -0.59
    Havolalar
    -0.59
    olished
    -0.58
    NameInMap
    -0.58
    ScopeManager
    -0.57
    POSITIVE LOGITS
     a
    0.56
     an
    0.50
    ynchron
    0.47
     unut
    0.44
     MainAxisSize
    0.44
    wall
    0.42
    paper
    0.41
     minors
    0.40
    map
    0.40
    tagon
    0.40
    Activations Density 0.001%

    No Known Activations