© 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. 5-CLT-HP
    7. 96267
    Prev
    Next
    INDEX
    Explanations

    which

    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
     feroit
    -0.70
     rangs
    -0.69
     déclen
    -0.68
     modalités
    -0.63
     auroit
    -0.61
    Personendaten
    -0.61
    LookAnd
    -0.59
    Джерела
    -0.59
     entraîner
    -0.59
     TestBed
    -0.57
    POSITIVE LOGITS
     the
    0.55
    ReusableCell
    0.54
     things
    0.50
    borderSide
    0.50
     AssemblyTitle
    0.49
     Guest
    0.47
     these
    0.47
    styleable
    0.47
    WithMany
    0.47
     those
    0.46
    Activations Density 0.002%

    No Known Activations