© 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. 0-CLT-HP
    7. 91172
    Prev
    Next
    INDEX
    Explanations

    demolition

    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
    
    -1.13
    CppMethod
    -1.04
     defaultstate
    -1.04
    NOPQRST
    -1.02
     depression
    -1.01
    providedIn
    -1.00
    IContainer
    -0.99
    depression
    -0.98
     disambiguazione
    -0.96
     AttributeSet
    -0.96
    POSITIVE LOGITS
     of
    0.91
    ly
    0.76
     in
    0.63
    able
    0.63
    ,
    0.63
     from
    0.62
    .
    0.62
    ides
    0.59
    ment
    0.59
    ies
    0.59
    Activations Density 0.640%

    No Known Activations