© 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. 0-CLT-HP
    4. 45132
    Prev
    Next
    INDEX
    Explanations

    {

    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
    MethodManager
    -0.69
     setOpen
    -0.65
     juridiques
    -0.65
    ]`
    -0.65
     sanitaires
    -0.64
     legales
    -0.64
     judiciales
    -0.63
    hyrchwyd
    -0.62
     SwitchCompat
    -0.62
     vậy
    -0.62
    POSITIVE LOGITS
     correctes
    0.54
    AddWithValue
    0.48
     enlistment
    0.48
    gatsby
    0.46
     Lav
    0.46
    enoid
    0.46
    faz
    0.46
     Lob
    0.44
     Fine
    0.44
     Car
    0.44
    Activations Density 0.161%

    No Known Activations